aeo-mcp

An MCP server that gives AI agents — Claude, Claude Code, Cursor, anything speaking the Model Context Protocol — tools to inspect a website's visibility to AI answer engines. Crawler permissions, llms.txt, structured data, on-page signals, and a full 29-check AI-readiness audit (powered by answer-audit), each one tool call away. Read-only, no API keys, no telemetry.

Real session: Claude Desktop discovers The Verge allows GPTBot (OpenAI licensing deal) while blocking ClaudeBot, PerplexityBot, Google-Extended, and CCBot — one tool call.

Install

Claude Code

claude mcp add aeo -- npx -y aeo-mcp

Claude Desktop (claude_desktop_config.json)

{ "mcpServers": { "aeo": { "command": "npx", "args": ["-y", "aeo-mcp"] } } }

Cursor (.cursor/mcp.json)

{ "mcpServers": { "aeo": { "command": "npx", "args": ["-y", "aeo-mcp"] } } }

Related MCP server: mcp-geo

Tools

Bots checked by check_ai_crawlers: GPTBot, ClaudeBot, PerplexityBot, Google-Extended, CCBot, Bingbot.

Try these prompts

• "Audit glowlab.com and summarize the top 3 AEO fixes."

• "Compare the AI crawler policies of nike.com and adidas.com — who is more open to being cited?"

• "Check if my site has a valid llms.txt, and if not, draft one from my page signals."

Security

The server fetches model-supplied URLs, so it ships with an SSRF guard: http/https only, DNS resolution checked against private and special ranges (loopback, RFC1918, link-local, unique-local, IPv4-mapped forms), re-validation on every redirect hop, 10 s timeout, 2 MB body cap, max 5 redirects. Violations return a clean tool error, never an exception. All tools are read-only and no LLM calls happen inside the server.

Development

npm install
npm run build   # required before npm test (the protocol test runs dist/)
npm test

Tests include a scripted stdio round-trip (initialize → tools/list → tools/call) against the built server. To inspect interactively:

npx @modelcontextprotocol/inspector node dist/index.js

License

MIT © Arthur Carlson